TY - GEN
T1 - Identifying connectivity patterns for brain diseases via multi-side-view guided deep architectures
AU - Zhang, Jingyuan
AU - Cao, Bokai
AU - Xie, Sihong
AU - Lu, Chun Ta
AU - Yu, Philip S.
AU - Ragin, Ann B.
N1 - Funding Information:
This work is supported in part by NSF through grants III-1526499, CNS-1115234, and OISE-1129076, and Google Research Award.
PY - 2016
Y1 - 2016
N2 - There is considerable interest in mining neuroimage data to discover clinically meaningful connectivity patterns to inform an understanding of neurological and neuropsychiatrie disorders. Subgraph mining models have been used to discover connected subgraph patterns. However, it is difficult to capture the complicated interplay among patterns. As a result, classification performance based on these results may not be satisfactory. To address this issue, we propose to learn non-linear representations of brain connectivity patterns from deep learning architectures. This is non-trivial, due to the limited subjects and the high costs of acquiring the data. Fortunately, auxiliary information from multiple side views such as clinical, serologic, immunologic, cognitive and other diagnostic testing also characterizes the states of subjects from different perspectives. In this paper, we present a novel Multi-side-View guided AutoEncoder (MVAE) that incorporates multiple side views into the process of deep learning to tackle the bias in the construction of connectivity patterns caused by the scarce clinical data. Extensive experiments show that MVAE not only captures discriminative connectivity patterns for classification, but also discovers meaningful information for clinical interpretation.
AB - There is considerable interest in mining neuroimage data to discover clinically meaningful connectivity patterns to inform an understanding of neurological and neuropsychiatrie disorders. Subgraph mining models have been used to discover connected subgraph patterns. However, it is difficult to capture the complicated interplay among patterns. As a result, classification performance based on these results may not be satisfactory. To address this issue, we propose to learn non-linear representations of brain connectivity patterns from deep learning architectures. This is non-trivial, due to the limited subjects and the high costs of acquiring the data. Fortunately, auxiliary information from multiple side views such as clinical, serologic, immunologic, cognitive and other diagnostic testing also characterizes the states of subjects from different perspectives. In this paper, we present a novel Multi-side-View guided AutoEncoder (MVAE) that incorporates multiple side views into the process of deep learning to tackle the bias in the construction of connectivity patterns caused by the scarce clinical data. Extensive experiments show that MVAE not only captures discriminative connectivity patterns for classification, but also discovers meaningful information for clinical interpretation.
UR - http://www.scopus.com/inward/record.url?scp=84991712816&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84991712816&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84991712816
T3 - 16th SIAM International Conference on Data Mining 2016, SDM 2016
SP - 36
EP - 44
BT - 16th SIAM International Conference on Data Mining 2016, SDM 2016
A2 - Venkatasubramanian, Sanjay Chawla
A2 - Meira, Wagner
PB - Society for Industrial and Applied Mathematics Publications
T2 - 16th SIAM International Conference on Data Mining 2016, SDM 2016
Y2 - 5 May 2016 through 7 May 2016
ER -